Improving AI-Generated Images, Pixel by Pixel

Improving AI-generated images, pixel by pixel

If you have ever used an artificial intelligence text-to-image generator like ChatGPT or Google Gemini, you may have encountered a common but maddening problem: The image looks nearly perfect, but when you ask the AI to fix one small detail, it messes up something unrelated.

New AI model could fix image details without changing everything else

Researchers have developed an AI image-generation model designed to give users finer control over individual pixels. The approach could help address a familiar frustration: fixing one detail in a picture only to find that other parts have changed too. The model, called PixelDiT2, works directly with an image’s colored dots rather than relying on the […]